打印

作者

来源

REGIONAL SCIENCE AND URBAN ECONOMICS,Vol.69,P.48-68

语言

英文

关键字

Spatial econometrics; Connectivity matrix; Salary benchmarking models; Markov Chain Monte Carlo estimation; Bayesian model probabilities; Convex combination; SPATIAL AUTOREGRESSIVE MODELS; SPECIFICATION; DISTURBANCES; ECONOMETRICS; MATRICES; TESTS

作者单位

[Debarsy, Nicolas] Univ Lille, LEM UMR 9221, CNRS, Cite Sci,Bat SH2, Villeneuve Dascq, France. [LeSage, James] Texas State Univ San Marcos, Dept Finance & Econ, 601 Univ Dr, San Marcos, TX 78666 USA. Debarsy, N (reprint author), Univ Lille, LEM UMR 9221, CNRS, Cite Sci,Bat SH2, Villeneuve Dascq, France. E-Mail: nicolas.debarsy@cnrs.fr; jlesage@spatial-econometrics.com

摘要

There is a great deal of literature regarding use of non-geographically based connectivity matrices or combinations of geographic and non-geographic structures in spatial econometrics models. We explore alternative approaches for constructing convex combinations of different types of dependence between observations. Pace and LeSage (2002) as well as Hazir et al. (2016) use convex combinations of different connectivity matrices to form a single weight matrix that can be used in conventional spatial regression estimation and inference. An example for the case of two weight matrices, W-1, W-2 reflecting different types of dependence between a cross-section of regions, firms, individuals etc., located in space would be: W-c = gamma(1) W-1+ (1 - gamma(1))W-2, 0 <= gamma(1) <= 1. The matrix W-c reflects a convex combination of the two weight matrices, with the scalar parameter gamma(1) indicating the relative importance assigned to each type of dependence. We explore issues that arise in producing estimates and inferences from these more general cross-sectional regression relationships in a Bayesian framework. We propose two procedures to estimate such models and assess their finite sample properties through Monte Carlo experiments. We illustrate our methodology in an application to CEO salaries for a sample of nursing homes located in Texas. Two types of weights are considered, one reflecting spatial proximity of nursing homes and the other peer group proximity, which arise from the salary benchmarking literature.